ML4GW / ML4GW/DeepClean

Fix probabilistic behavior in PSD loss test in `deepclean.trainer`

Open
#56 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bug documentation good first issue
Dominant language
Python
Stars
10
Forks
6
PR merge metrics
No merged PRs in 30d

Description

test_criterion.test_psd_loss in the deepclean.trainer library uses random data to test the PSD and relies on statistics to keep its values in an acceptable range, causing random failures. This test should be made more deterministic and test for the expected behavior more directly.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reading test_criterion.test_psd_loss in the deepclean.trainer tests and identify which random inputs and statistical assertions make it flaky. Replace the probabilistic setup with deterministic checks of the expected PSD-loss behavior, then run this test repeatedly to confirm it no longer fails randomly.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
testing-qa
Issue type
Refactor
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.